Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Java annotations and serialized names in class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "private" in Java/C++ code

    np_acts-logits-general · gemini-2.0-flash

    private keyword in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    -0.51
    어
    -0.49
    δό
    -0.48
    lah
    -0.48
     "
    -0.47
    โ
    -0.45
    닝
    -0.44
     التن
    -0.44
    echo
    -0.44
     overall
    -0.44
    POSITIVE LOGITS
    private
    2.25
     private
    1.99
     PRIVATE
    1.52
     Private
    1.52
     privately
    1.36
    Private
    1.35
     prywat
    1.35
     privata
    1.33
     privat
    1.32
     privé
    1.31
    Act Density 0.039%

    No Known Activations